Here I want to plot (style_score, content_score and loss) vs iteration line graph in a single graph. How do I plot using matplotlib? Here is my code:
def run_style_transfer(cnn, normalization_mean, normalization_std,
content_img, style_img, input_img, num_steps=300,
style_weight=1000000, content_weight=1):
"""Run the style transfer."""
print('Building the style transfer model..')
model, style_losses, content_losses = get_style_model_and_losses(cnn,
normalization_mean, normalization_std, style_img, content_img)
optimizer = get_input_optimizer(input_img)
print('Optimizing..')
run = [0]
while run[0] <= num_steps:
def closure():
# correct the values of updated input image
input_img.data.clamp_(0, 1)
optimizer.zero_grad()
model(input_img)
style_score = 0
content_score = 0
for sl in style_losses:
style_score += sl.loss
for cl in content_losses:
content_score += cl.loss
style_score *= style_weight
content_score *= content_weight
loss = style_score + content_score
loss.backward()
run[0] += 1
if run[0] % 50 == 0:
print("run {}:".format(run))
print('Style Loss : {:4f} Content Loss: {:4f}'.format(
style_score.item(), content_score.item()))
print()
return style_score + content_score
optimizer.step(closure)
# a last correction to have the tensors between 0 and 1
input_img.data.clamp_(0, 1)
return input_img
output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_img, style_img, input_img, num_steps=800)
Building the style transfer model..
Optimizing..
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:7: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
import sys
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:8: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
run [50]:
Style Loss : 146.929642 Content Loss: 26.714472
run [100]:
Style Loss : 20.721758 Content Loss: 25.548061
run [150]:
Style Loss : 5.534753 Content Loss: 22.413723
run [200]:
Style Loss : 2.631659 Content Loss: 19.817213
run [250]:
Style Loss : 1.682667 Content Loss: 17.917061
run [300]:
Style Loss : 1.305469 Content Loss: 16.689680
run [350]:
Style Loss : 1.066183 Content Loss: 15.843134
run [400]:
Style Loss : 0.952005 Content Loss: 15.269234
run [450]:
Style Loss : 0.827443 Content Loss: 14.904546
run [500]:
Style Loss : 0.791187 Content Loss: 14.578773
run [550]:
Style Loss : 0.808383 Content Loss: 14.343610
run [600]:
Style Loss : 0.771382 Content Loss: 14.127987
run [650]:
Style Loss : 0.811431 Content Loss: 13.953921
run [700]:
Style Loss : 0.768540 Content Loss: 13.791541
run [750]:
Style Loss : 0.713468 Content Loss: 13.682455
run [800]:
Style Loss : 0.724343 Content Loss: 13.602742
Expected result:
